Inference Acceleration for Large Language Models on CPUs
This addresses the computational and environmental challenges of deploying LLMs in real-world applications, though it is an incremental improvement on existing CPU optimization techniques.
The paper tackles the problem of inefficient inference for large language models (LLMs) by developing a CPU-based acceleration method that exploits parallel processing and batching, achieving an 18-22x improvement in tokens per second and reducing power consumption by 48.9%.
In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% while providing production ready throughput and latency.